Dynamic Facial Expression Recognition Using Boosted Component-Based Spatiotemporal Features and Multi-classifier Fusion
نویسندگان
چکیده
Feature extraction and representation are critical in facial expression recognition. The facial features can be extracted from either static images or dynamic image sequences. However, static images may not provide as much discriminative information as dynamic image sequences. On the other hand, from the feature extraction point of view, geometric features are often sensitive to the shape and resolution variations, whereas appearance based features may contain redundant information. In this paper, we propose a component-based facial expression recognition method by utilizing the spatiotemporal features extracted from dynamic image sequences, where the spatiotemporal features are extracted from facial areas centered at 38 detected fiducial interest points. Considering that not all features are important to the facial expression recognition, we use the AdaBoost algorithm to select the most discriminative features for expression recognition. Moreover, based on median rule, mean rule, and product rule of the classifier fusion strategy, we also present a framework for multi-classifier fusion to improve the expression classification accuracy. Experimental studies conducted on the Cohn-Kanade database show that our approach that combines both boosted component-based spatiotemporal features and multi-classifier fusion strategy provides a better performance for expression recognition compared with earlier approaches.
منابع مشابه
Boosted multi-resolution spatiotemporal descriptors for facial expression recognition
Recently, a spatiotemporal local binary pattern operator from three orthogonal planes (LBP-TOP) was proposed for describing and recognizing dynamic textures and applied to facial expression recognition. In this paper, we extend the LBP-TOP features to multi-resolution spatiotemporal space and use them for describing facial expressions. AdaBoost is utilized to learn the principal appearance and ...
متن کاملFacial Expression Recognition Based on Anatomical Structure of Human Face
Automatic analysis of human facial expressions is one of the challenging problems in machine vision systems. It has many applications in human-computer interactions such as, social signal processing, social robots, deceit detection, interactive video and behavior monitoring. In this paper, we develop a new method for automatic facial expression recognition based on facial muscle anatomy and hum...
متن کاملA COMPARATIVE ANALYSIS OF WAVELET-BASED FEMG SIGNAL DENOISING WITH THRESHOLD FUNCTIONS AND FACIAL EXPRESSION CLASSIFICATION USING SVM AND LSSVM
This work presents a technique for the analysis of Facial Electromyogram signal activities to classify five different facial expressions for Computer-Muscle Interfacing applications. Facial Electromyogram (FEMG) is a technique for recording the asynchronous activation of neuronal inside the face muscles with non-invasive electrodes. FEMG pattern recognition is a difficult task for the researche...
متن کاملSpatiotemporal Features for Effective Facial Expression Recognition
We consider two novel representations and feature extraction schemes for automatic recognition of emotion related facial expressions. In one scheme facial landmark points are tracked over successive video frames using an effective detector and tracker to extract landmark trajectories. Features are extracted from landmark trajectories using Independent Component Analysis (ICA) method. In the alt...
متن کاملFacial Expression Recognition Based on Structural Changes in Facial Skin
Facial expressions are the most powerful and direct means of presenting human emotions and feelings and offer a window into a persons’ state of mind. In recent years, the study of facial expression and recognition has gained prominence; as industry and services are keen on expanding on the potential advantages of facial recognition technology. As machine vision and artificial intelligence advan...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2010